© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15820
    Prev
    Next
    INDEX
    Explanations

    boy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boy
    -0.76
     boy
    -0.75
    Boy
    -0.67
     BOY
    -0.65
    男孩
    -0.60
    boy
    -0.60
    BOY
    -0.50
     Boyd
    -0.47
     Boys
    -0.46
    彝
    -0.41
    POSITIVE LOGITS
     Majefty
    0.90
     CreateTagHelper
    0.85
     jsPsych
    0.85
     myſelf
    0.84
    Tikang
    0.82
     Shakspeare
    0.80
    tagHelperRunner
    0.80
    存于互联网档案馆
    0.79
     onPostExecute
    0.79
     Forumite
    0.78
    Activations Density 0.003%

    No Known Activations